© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8770
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unrecognized
    -0.26
     pitches
    -0.24
    (define
    -0.24
    èµĬ
    -0.24
    ICATION
    -0.24
    asions
    -0.23
    æĶĺ
    -0.23
    ildo
    -0.23
     abund
    -0.23
    endregion
    -0.23
    POSITIVE LOGITS
    nip
    0.27
    odes
    0.26
    BX
    0.26
    eva
    0.26
    eft
    0.26
    ante
    0.25
    æµģæ°´
    0.25
    æ¯ĶæĪij
    0.25
     Behaviour
    0.24
    åİĨåı²æĢ§
    0.24
    Activations Density 0.278%

    No Known Activations

    This feature has no known activations.